Absolute longitudinal localization of a moving object on the non-linear sections of a trajectory described by a continuous curve

Abstract

Techniques for determining an absolute longitudinal position of a moving object on non-linear sections of a trajectory are described. In one technique, an estimated track boundary segment is generated based on a digital image associated with a moving object. For each position of multiple positions in an actual track boundary segment pertaining to a track for one or more moving objects, an alignment of the estimated track boundary segment with the actual track boundary segment is made based on that position. Also, based on the alignment, a difference measurement between the estimated track boundary segment and a portion of the actual track boundary segment is generated. After each of the positions is considered, a particular alignment, of multiple alignments, that is associated with the lowest difference measurement among the multiple positions is selected. Based on the particular alignment, a longitudinal value of the moving object is determined.

What is claimed is: 
     
         1 . A method comprising:
 generating an estimated track boundary segment based on a digital image associated with a moving object;   for each position of a plurality of positions in an actual track boundary segment pertaining to a track for one or more moving objects:
 based on said each position, making an alignment of the estimated track boundary segment with the actual track boundary segment; 
 based on the alignment, generating a difference measurement between the estimated track boundary segment and a portion of the actual track boundary segment; 
   selecting a particular alignment, of a plurality of alignments, that is associated with the lowest difference measurement among the plurality of positions;   based on the particular alignment, determining a longitudinal value of the moving object;   wherein the method is performed by one or more computing devices.   
     
     
         2 . The method of  claim 1 , wherein determining the longitudinal value comprises:
 based on the particular alignment, determining a point on the actual track boundary segment that is associated with the particular alignment of the estimated track boundary segment with the actual track boundary segment;   identifying the longitudinal value that is associated with the point.   
     
     
         3 . The method of  claim 1 , wherein the estimated track boundary segment is a first estimated track boundary segment that is associated with a first boundary of the track, wherein the particular alignment is a first particular alignment, wherein the longitudinal value is a first longitudinal value, the method further comprising:
 generating a second estimated track boundary segment based on the digital image;   for each position of a second plurality of positions in a second actual track boundary segment pertaining to the track:
 based on each position, making a second alignment of the second estimated track boundary segment with the second actual track boundary segment; 
 based on the second alignment, generating a second difference measurement between the second estimated track boundary segment and a portion of the second actual track boundary segment; 
   selecting a second particular alignment, of a second plurality of alignments, that is associated with the lowest difference measurement among the second plurality of positions;   based on the second particular alignment, determining a second longitudinal value of the moving object.   
     
     
         4 . The method of  claim 3 , further comprising:
 generating a final longitudinal value of the moving object based on the first longitudinal value and the second longitudinal value.   
     
     
         5 . The method of  claim 4 , further comprising:
 determining whether the moving object is closer to the first estimated track boundary segment or to the second estimated track boundary;   wherein generating the final longitudinal value comprises applying more weight to the first longitudinal value than to the second longitudinal value in response to determining that the moving object is closer to the first estimated track boundary segment than to the second estimated track boundary segment.   
     
     
         6 . The method of  claim 4 , further comprising:
 generating a first uncertainty value that is associated with the first longitudinal value;   generating a second uncertainty value that is associated with the second longitudinal value;   wherein generating the final longitudinal value is also based on the first uncertainty value and the second uncertainty value.   
     
     
         7 . The method of  claim 4 , further comprising:
 determining an uncertainty of the first particular alignment of the first estimated track boundary segment and an uncertainty of the second particular alignment of the second estimated track boundary segment;   wherein generating the final longitudinal value comprises applying more weight to the first longitudinal value than to the second longitudinal value in response to determining which alignment is more uncertain than the other.   
     
     
         8 . The method of  claim 1 , further comprising:
 for each alignment of the plurality of alignments:
 determining a difference between the difference measurement of said each alignment and the lowest difference measurement; 
 adding the difference to a set of differences; 
   generating an uncertainty value for the particular alignment based on the set of differences.   
     
     
         9 . The method of  claim 8 , further comprising:
 for each alignment of the plurality of alignments:
 determining a normalized difference between the difference measurement of said each alignment and the lowest difference measurement; 
 wherein generating the uncertainty value for the particular alignment is also based on the normalized difference. 
   
     
     
         10 . The method of  claim 1 , further comprising:
 storing ground truth data about an actual track boundary, of which the actual track boundary segment is a part;   wherein the actual track boundary comprises a set of positions, each of which is associated with a longitudinal value;   wherein the plurality of positions is a strict subset of the set of positions;   
     
     
         11 . The method of  claim 10 , further comprising:
 generating an uncertainty value for the particular alignment based on the set of differences;   for a second digital image that is subsequent to the digital image, determining a search area size of the actual track boundary based on the uncertainty value;   wherein a number of positions of the actual track boundary to consider for aligning a second actual track boundary segment with a second estimated track boundary segment, that is generated based on the second digital image, is directly proportional to the search area size.   
     
     
         12 . The method of  claim 10 , further comprising:
 for a second digital image that is subsequent to the digital image, determining a search area size of the actual track boundary based on an approximate position of the moving object and a known error of the approximate position.   
     
     
         13 . The method of  claim 10 , further comprising:
 for a second digital image that is subsequent to the digital image, determining a search area size of the actual track boundary based on an amount of time that has passed since the moving object began moving in a controlled environment.   
     
     
         14 . One or more non-transitory storage media storing instructions which, when executed by one or more computing devices, cause:
 generating an estimated track boundary segment based on a digital image associated with a moving object;   for each position of a plurality of positions in an actual track boundary segment pertaining to a track for one or more moving objects:
 based on said each position, making an alignment of the estimated track boundary segment with the actual track boundary segment; 
 based on the alignment, generating a difference measurement between the estimated track boundary segment and a portion of the actual track boundary segment; 
   selecting a particular alignment, of a plurality of alignments, that is associated with the lowest difference measurement among the plurality of positions;   based on the particular alignment, determining a longitudinal value of the moving object.   
     
     
         15 . The one or more storage media of  claim 14 , wherein determining the longitudinal value comprises:
 based on the particular alignment, determining a point on the actual track boundary segment that is associated with the particular alignment of the estimated track boundary segment with the actual track boundary segment;   identifying the longitudinal value that is associated with the point.   
     
     
         16 . The one or more storage media of  claim 14 , wherein the estimated track boundary segment is a first estimated track boundary segment that is associated with a first boundary of the track, wherein the particular alignment is a first particular alignment, wherein the longitudinal value is a first longitudinal value, wherein the instructions, when executed by the one or more computing devices, further cause:
 generating a second estimated track boundary segment based on the digital image;   for each position of a second plurality of positions in a second actual track boundary segment pertaining to the track:
 based on each position, making a second alignment of the second estimated track boundary segment with the second actual track boundary segment; 
 based on the second alignment, generating a second difference measurement between the second estimated track boundary segment and a portion of the second actual track boundary segment; 
   selecting a second particular alignment, of a second plurality of alignments, that is associated with the lowest difference measurement among the second plurality of positions;   based on the second particular alignment, determining a second longitudinal value of the moving object.   
     
     
         17 . The one or more storage media of  claim 16 , wherein the instructions, when executed by the one or more computing devices, further cause:
 generating a final longitudinal value of the moving object based on the first longitudinal value and the second longitudinal value.   
     
     
         18 . The one or more storage media of  claim 17 , wherein the instructions, when executed by the one or more computing devices, further cause:
 determining whether the moving object is closer to the first estimated track boundary segment or to the second estimated track boundary;   wherein generating the final longitudinal value comprises applying more weight to the first longitudinal value than to the second longitudinal value in response to determining that the moving object is closer to the first estimated track boundary segment than to the second estimated track boundary segment.   
     
     
         19 . The one or more storage media of  claim 17 , wherein the instructions, when executed by the one or more computing devices, further cause:
 generating a first uncertainty value that is associated with the first longitudinal value;   generating a second uncertainty value that is associated with the second longitudinal value;   wherein generating the final longitudinal value is also based on the first uncertainty value and the second uncertainty value.   
     
     
         20 . The one or more storage media of  claim 17 , wherein the instructions, when executed by the one or more computing devices, further cause:
 determining an uncertainty of the first particular alignment of the first estimated track boundary segment and an uncertainty of the second particular alignment of the second estimated track boundary segment;   wherein generating the final longitudinal value comprises applying more weight to the first longitudinal value than to the second longitudinal value in response to determining which alignment is more uncertain than the other.